winston-ai-mcp

Winston AI MCP Server ⚡️

Model Context Protocol (MCP) Server for Winston AI - the most accurate AI Detector. Detect AI-generated content, plagiarism, and compare texts with ease.

✨ Features

🔍 AI Text Detection

• Human vs AI Classification: Determine if text was written by a human or AI
• Confidence Scoring: Get percentage-based confidence scores
• Sentence-level Analysis: Identify the most AI-like sentences in your text
• Multi-language Support: Works with text in various languages
• Credit cost: 1 credit per word

🖼️ AI Image Detection

• Image Analysis: Detect AI-generated images using advanced ML models
• Metadata Verification: Analyze image metadata and EXIF data
• Watermark Detection: Identify AI watermarks and their issuers
• Multiple Formats: Supports JPG, JPEG, PNG, and WEBP formats
• Credit cost: 300 credits per image

📝 Plagiarism Detection

• Internet-wide Scanning: Check against billions of web pages
• Source Identification: Find and list original sources
• Detailed Reports: Get comprehensive plagiarism analysis
• Academic & Professional Use: Perfect for content verification
• Credit cost: 2 credits per word

🔄 Text Comparison

• Similarity Analysis: Compare two texts for similarities
• Word-level Matching: Detailed breakdown of matching content
• Percentage Scoring: Get precise similarity percentages
• Bidirectional Analysis: Compare both directions
• Credit cost: 1/2 credit per total words found in both texts

🚀 Quick Start

Prerequisites

• Node.js 18+
• Winston AI API Key (Get one here)

🛠️ Development

Running with npx 🔋

env WINSTONAI_API_KEY=your-api-key npx -y winston-ai-mcp

Running the MCP Server locally via stdio 💻

Create a .env file in your project root:

WINSTONAI_API_KEY=your_actual_api_key_here

# Clone the repository
git clone https://github.com/gowinston-ai/winston-ai-mcp-server.git
cd winston-ai-mcp-server

# Install dependencies
npm install

# Build the project and start the server
npm run mcp-start

📦 Docker Support

Build and run with Docker:

# Build the image
docker build -t winston-ai-mcp .

# Run the container
docker run -e WINSTONAI_API_KEY=your_api_key winston-ai-mcp

📋 Available Scripts

• npm run build - Compile TypeScript to JavaScript
• npm start - Start the MCP server
• npm run mcp-start - Compile TypeScript to JavaScript and Start the MCP server
• npm run lint - Run ESLint for code quality
• npm run format - Format code with Prettier

🔧 Configuration

For Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "winston-ai-mcp": {
      "command": "npx",
      "args": ["-y", "winston-ai-mcp"],
      "env": {
        "WINSTONAI_API_KEY": "your-api-key"
      }
    }
  }
}

For Cursor IDE

Add to your Cursor configuration:

{
  "mcpServers": {
    "winston-ai-mcp": {
      "command": "npx",
      "args": ["-y", "winston-ai-mcp"],
      "env": {
        "WINSTONAI_API_KEY": "your-api-key"
      }
    }
  }
}

Accessing the MCP Server via API 🌐

The server is at https://api.gowinston.ai/mcp/v1 over HTTPS Streamable HTTP (JSON responses). MCP clients (Cursor, MCP Inspector) should use that URL and transport. You can also call it with curl.

Example: List tools

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--header 'jsonrpc: 2.0' \
--data '{
  "jsonrpc": "2.0",
  "method": "tools/list",
  "id": 1
}'

Example: AI Text Detection

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ai-text-detection",
    "arguments": {
      "text": "Your text to analyze (minimum 300 characters)",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'

Example: AI Image Detection

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "ai-image-detection",
    "arguments": {
      "url": "https://example.com/image.jpg",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'

Example: Plagiarism Detection

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "plagiarism-detection",
    "arguments": {
      "text": "Text to check for plagiarism (minimum 100 characters)",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'

Note: Replace your-winston-ai-api-key with your actual Winston AI API key. You can get one at https://dev.gowinston.ai.

📋 API Reference

AI Text Detection

{
  "text": "Your text to analyze (600+ characters recommended)",
  "file": "(optional) A file to scan. If you supply a file, the API will scan the content of the file. The file must be in plain .pdf, .doc or .docx format.",
  "website": "(optional) A website URL to scan. If you supply a website, the API will fetch the content of the website and scan it. The website must be publicly accessible."
}

AI Image Detection

{
  "url": "https://example.com/image.jpg"
}

Plagiarism Detection

{
  "text": "Text to check for plagiarism",
  "language": "en", // optional, default: "en"
  "country": "us"   // optional, default: "us"
}

Text Comparison

{
  "first_text": "First text to compare",
  "second_text": "Second text to compare"
}

🤝 Contributing

We welcome contributions!

• Fork the repository
• Create a feature branch (git checkout -b feature/amazing-feature)
• Commit your changes (git commit -m 'Add amazing feature')
• Push to the branch (git push origin feature/amazing-feature)
• Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Links

• Winston AI MCP NPM Package: https://www.npmjs.com/package/winston-ai-mcp
• Winston AI Website: https://gowinston.ai
• API Documentation: https://dev.gowinston.ai
• MCP Protocol: https://modelcontextprotocol.io
• GitHub Repository: https://github.com/gowinston-ai/winston-ai-mcp-server

⭐ Support

If you find this project helpful, please give it a star on GitHub!

Made with ❤️ by the Winston AI Team